cali_wildfires_superbuckets

This model is a fine-tuned version of gdurkin/cali_wildfires on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 39.8611

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 5e-05
• train_batch_size: 2
• eval_batch_size: 2
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 8
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.05
• num_epochs: 30

Training results

Training Loss	Epoch	Step	Validation Loss
46.9823	0.9992	908	44.2028
43.7026	1.9994	1817	41.6333
43.1604	2.9997	2726	42.6112
42.7701	4.0	3635	41.1723
42.448	4.9992	4543	41.7719
42.1016	5.9994	5452	41.3481
41.7597	6.9997	6361	40.7160
41.931	8.0	7270	40.4156
40.8349	8.9992	8178	41.7616
41.4868	9.9994	9087	39.8706
40.8336	10.9997	9996	40.9914
40.5751	12.0	10905	40.6050
40.587	12.9992	11813	40.2944
40.2109	13.9994	12722	40.7404
40.7232	14.9997	13631	40.0876
40.0984	16.0	14540	40.0743
40.121	16.9992	15448	39.3861
39.6405	17.9994	16357	39.7561
39.7266	18.9997	17266	39.7452
39.216	20.0	18175	39.9445
39.4727	20.9992	19083	40.1958
39.6189	21.9994	19992	40.1457
39.622	22.9997	20901	40.0345
38.9822	24.0	21810	39.8065
39.4845	24.9992	22718	39.8453
39.2516	25.9994	23627	39.8971
39.099	26.9997	24536	39.8205
38.8892	28.0	25445	39.7963
38.7629	28.9992	26353	39.6499
38.6387	29.9752	27240	39.8611

Framework versions

• Transformers 4.45.2
• Pytorch 2.4.1+cu124
• Datasets 2.21.0
• Tokenizers 0.20.3